DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning

[2503.11892] DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2503.11892 (cs) [Submitted on 14 Mar 2025 ( v1 ), last revised 11 Apr 2026 (this version, v3)] Title: DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning Authors: Chengxuan Qian , Shuo Xing , Shawn Li , Yue Zhao , Zhengzhong Tu View a PDF of the paper titled DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning, by Chengxuan Qian and 4 other authors View PDF HTML (experimental) Abstract: Multimodal representation learning aims to capture both shared and complementary semantic information across multiple modalities. However, the intrinsic heterogeneity of diverse modalities presents substantial challenges to achieve effective cross-modal collaboration and integration. To address this, we introduce DecAlign, a novel hierarchical cross-modal alignment framework designed to decouple multimodal representations into modality-unique (heterogeneous) and modality-common (homogeneous) features. For handling heterogeneity, we employ a prototype-guided optimal transport alignment strategy leveraging gaussian mixture modeling and multi-marginal transport plans, thus mitigating distribution discrepancies while preserving modality-unique characteristics. To reinforce homogeneity, we ensure semantic consistency across modalities by aligning latent distribution matching with Maximum Mean Discrepancy regularization. Furthermore, we incorporate a multimodal transformer to enhance high-level semantic feature fusion, thereby further reducing cross-modal inconsistencies. Our extensive experiments on four widely used multimodal benchmarks demonstrate that DecAlign consistently outperforms existing state-of-the-art methods across five metrics. These results highlight the efficacy of DecAlign in enhancing superior cross-modal alignment and semantic consistency while preserving modality-unique features, marking a significant advancement in multimodal representation learning scenarios. Our project page is at this https URL . Comments: Accepted by ICLR 2026 Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2503.11892 [cs.CV] (or arXiv:2503.11892v3 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2503.11892 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Chengxuan Qian [ view email ] [v1] Fri, 14 Mar 2025 21:47:48 UTC (2,648 KB) [v2] Mon, 29 Sep 2025 22:31:06 UTC (1,107 KB) [v3] Sat, 11 Apr 2026 05:18:32 UTC (1,460 KB) Full-text links: Access Paper: View a PDF of the paper titled DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning, by Chengxuan Qian and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2025-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Seeing the imagined: latent functional alignment in visual imagery decoding from fMRI data#1061702
• When to Align, When to Predict: A Phase Diagram for Multimodal Learning#985128
• MARS: What Retrieval Signals Are Hidden in Multimodal Large Language Models for Text-Video Retrieval?#924722
• MARS: What Retrieval Signals Are Hidden in Multimodal Large Language Models for Text-Video Retrieval?#920488
• UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation#1014830